commit

.gitignore

@@ -3,7 +3,8 @@
 /m2_annotations
 evaluation/spice/*
 *.pyc
+*.jar
 /saved_transformer_models
-/tensorboard_logs
+tensorboard_logs
 /visualization
 /.vscode

README.md

@@ -82,6 +82,7 @@ We provide pretrained model [here](https://drive.google.com/file/d/1Y133r4Wd9edi
 |   Reproduced Model (ResNext101) 	|   81.2   	| 39.9 	| 29.6 	|   59.1  	|  133.7 	|  23.3|
 
 
+
 ### Online Evaluation
 We also report the performance of our model on the online COCO test server with an ensemble of four S<sup>2</sup> models. The detailed online test code can be obtained in this [repo](https://github.com/zhangxuying1004/RSTNet).
 

test_transformer.py

@@ -53,11 +53,11 @@ def predict_captions(model, dataloader, text_field):
     parser.add_argument('--workers', type=int, default=4)
     parser.add_argument('--m', type=int, default=40)
 
-    parser.add_argument('--features_path', type=str, default='./X101-features/X101_grid_feats_coco_trainval.hdf5')
+    parser.add_argument('--features_path', type=str, default='./X101_grid_feats_coco_trainval.hdf5')
     parser.add_argument('--annotation_folder', type=str, default='./m2_annotations')
 
-    # the path of tested model and vocabulary  
-    parser.add_argument('--model_path', type=str, default='saved_transformer_models/s2_checkpoint.pth')
+    # the path of tested model and vocabulary
+    parser.add_argument('--model_path', type=str, default='saved_transformer_models/demo_rl_v5_best_test.pth')
     parser.add_argument('--vocab_path', type=str, default='vocab.pkl')
     parser.add_argument('--num_clusters', type=int, default=5)
     args = parser.parse_args()